This paper presents Papilusion, an AI-generated scientific text detector developed within the DAGPap24 shared task on detecting automatically generated scientific papers. We propose an ensemble-based approach and conduct ablation studies to analyze the effect of the detector configurations on the performance. Papilusion is ranked 6th on the leaderboard, and we improve our performance after the competition ended, achieving 99.46 (+9.63) of the F1-score on the official test set.
@article{arxiv.2407.17629,
title = {Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers},
author = {Nikita Andreev and Alexander Shirnin and Vladislav Mikhailov and Ekaterina Artemova},
journal= {arXiv preprint arXiv:2407.17629},
year = {2024}
}
Comments
to appear in "The 4th Workshop on Scholarly Document Processing @ ACL 2024" proceedings